Unverified50% confidenceFactExact time
Indirect Prompt Injection was systematically elaborated by security researcher Kai Greshake and colleagues in a 2023 paper.
1
Sources
50%
Confidence
Long-term
Relevance
8/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn 2023, Kai Greshake and colleagues at Ruhr University Bochum in Germany were the first to systematically classify and assess the hazards of indirect prompt injection attacks in a research paper.77% similarUnverified研究人员Kai Greshake等人在2023年发表的论文《Not What You've Signed Up For》系统性地揭示了间接提示注入的威胁模型68% similarVerifiedPrompt Injection was first publicly demonstrated by security researcher Riley Goodside in 202264% similarUnverified2023年卡内基梅隆大学与德国CISPA亥姆霍兹信息安全中心的研究团队发表论文，证明当时主流LLM Agent对间接提示注入攻击高度脆弱，成功率超过80%60% similarUnverified2023年研究者已经演示了通过间接注入控制Bing Chat代理行为的概念验证攻击57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/796913API
curl https://kongchang.com/api/v1/knowledge/claims/796913MCP
get_claim(id=796913)